Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Φ-Space ST: A platform-agnostic method to identify cell states in spatial transcriptomics studies.

Cell reports methods·2026
Same author

Multi-Omics Reveals Early Pregnancy Placental Dysfunction Associated With Preterm and Term Preeclampsia.

MedComm·2026
Same author

Integrated lipidome and miRNome analyses reveal sex-based differences in circulating extracellular vesicles of alcohol use disorder patients.

Cell biology and toxicology·2026
Same author

Integrated transcriptomic and clinical analysis of autism spectrum disorder reveals structured heterogeneity and links Methyl-CpG Binding Domain Protein 2 expression with symptom severity.

Psychiatry and clinical neurosciences·2026
Same author

phylobar: an R package for multiresolution compositional barplots in omics studies.

Bioinformatics (Oxford, England)·2026
Same author

Scalable cell-specific coexpression networks for granular regulatory pattern discovery with NeighbourNet.

Genome research·2026

Related Experiment Video

Updated: Jun 21, 2026

Transcriptome Profiling of In-Vivo Produced Bovine Pre-implantation Embryos Using Two-color Microarray Platform
09:04

Transcriptome Profiling of In-Vivo Produced Bovine Pre-implantation Embryos Using Two-color Microarray Platform

Published on: January 30, 2017

Predicting qualitative phenotypes from microarray data - the Eadgene pig data set.

Christèle Robert-Granié1, Kim-Anh Lê Cao, Magali Sancristobal

  • 1INRA, UR631 Station d'Amélioration Génétique des Animaux, F-31326 Castanet-Tolosan, France. christele.robert-granie@toulouse.inra.fr

BMC Proceedings
|July 21, 2009
PubMed
Summary
This summary is machine-generated.

Machine learning and sparse Partial Least Squares (PLS) methods effectively identify biomarkers in pig transcriptomic data. Sparse PLS offers superior prediction and interpretability compared to standard PLS.

More Related Videos

Quantifying Abdominal Pigmentation in Drosophila melanogaster
08:41

Quantifying Abdominal Pigmentation in Drosophila melanogaster

Published on: June 1, 2017

Reverse Genetic Approach to Identify Regulators of Pigmentation using Zebrafish
07:16

Reverse Genetic Approach to Identify Regulators of Pigmentation using Zebrafish

Published on: March 1, 2022

Related Experiment Videos

Last Updated: Jun 21, 2026

Transcriptome Profiling of In-Vivo Produced Bovine Pre-implantation Embryos Using Two-color Microarray Platform
09:04

Transcriptome Profiling of In-Vivo Produced Bovine Pre-implantation Embryos Using Two-color Microarray Platform

Published on: January 30, 2017

Quantifying Abdominal Pigmentation in Drosophila melanogaster
08:41

Quantifying Abdominal Pigmentation in Drosophila melanogaster

Published on: June 1, 2017

Reverse Genetic Approach to Identify Regulators of Pigmentation using Zebrafish
07:16

Reverse Genetic Approach to Identify Regulators of Pigmentation using Zebrafish

Published on: March 1, 2022

Area of Science:

  • Genomics
  • Bioinformatics
  • Statistical Modeling

Background:

  • Utilized the Pig data set from Hazard et al. (2008) for analysis.
  • Data comprised 3686 gene expressions from 24 animals across 2 genotypes and 2 treatments.
  • Objective was to identify biomarkers distinguishing genotypes and treatments.

Purpose of the Study:

  • Evaluate the performance of two predictive statistical tools.
  • Compare Random Forest, Partial Least Squares (PLS), and sparse PLS.
  • Identify biomarkers for genotype and treatment in pig gene expression data.

Main Methods:

  • Applied Random Forest for predictive variable selection.
  • Compared classical Partial Least Squares (PLS) regression.
  • Introduced and evaluated sparse PLS, a variant with lasso penalization for variable selection.

Main Results:

  • All tested methods demonstrated strong performance on the dataset.
  • Sparse PLS exhibited enhanced prediction accuracy over standard PLS.
  • Sparse PLS improved the interpretability of the obtained results.

Conclusions:

  • Recommends machine learning (Random Forest) and multivariate (sparse PLS) methods for predictive tasks.
  • Highlights the suitability of these methods for high-dimensional transcriptomic data.
  • Emphasizes the advantage of sparse PLS in prediction and interpretability.